Tools
Tools
Singhwal, Prakhar (2025) A Novel Adaptive Energy-Aware Differential Evolution Algorithm for Fog Computing Optimization. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (612kB) | Preview |
Abstract
The expansion in the Internet of Things (IOT) devices has made room for a phenomenal increase in the output produced and instantaneous processing capacity. Traditional distributed computing systems, though efficient, seldom overlook energy-efficiency crucial for present IOT systems. Fog computing serves as an intermediary between cloud data centers and edge devices and are hosted near the edge nodes to lessen the response time and increase near source application execution efficiency. Nevertheless, these in-between nodes need to be in vicinity of the edge devices as they have limited processing power, especially in terms of energy. The best performing models focus on many metrics such as CPU Utilization, resource utilization often omitting energy efficiency. To conquer this disparity, the research proposes a novel adaptive differential evolution (ADE) algorithm which adapts dynamically to changing fog environment. The focus is to achieve exceptional task scheduling in a fog environment to cut down energy consumption keeping in mind that the other metrics remain unchanged. The outlined approach will be backed by a simulation tool (iFogSim) and will be measured against existing static and meta-heuristic algorithms. The designed solution is benchmarked at 50,100 and then 200 fog devices to see its effectiveness. Through the simulation, it was seen that the developed solution consumed 8.83% less energy than current state of art methods when evaluated at an intense workload of 200 fog devices.
Actions (login required)
 |
View Item |